Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4822 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.9714. Min Act: -0.0000

Data Index: 506039 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.9069. Min Act: -0.0000

Data Index: 1143952 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.2959. Min Act: -0.0000

Data Index: 770499 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.4305. Min Act: -0.0000

Data Index: 1064503 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.2284. Min Act: -0.0000

Data Index: 1253544 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.1454. Min Act: -0.0000

Data Index: 127109 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.0740. Min Act: -0.0000

Data Index: 372730 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.0982. Min Act: -0.0000

Data Index: 1231212 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.1042. Min Act: -0.0000

Data Index: 561955 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 4.9714. Min Range: -4.9714

Max Act: 3.8315. Min Act: -0.0000

Data Index: 754842 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 4.9714. Min Range: -4.9714

Max Act: 3.7872. Min Act: -0.0000

Data Index: 539457 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 4.9714. Min Range: -4.9714

Max Act: 3.8132. Min Act: -0.0000

Data Index: 244812 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 4.9714. Min Range: -4.9714

Max Act: 3.7866. Min Act: -0.0000

Data Index: 961132 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 4.9714. Min Range: -4.9714

Max Act: 3.9403. Min Act: -0.0000

Data Index: 1091567 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 4.9714. Min Range: -4.9714

Max Act: 3.7609. Min Act: -0.0000

Data Index: 1358479 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 4.9714. Min Range: -4.9714

Max Act: 3.6047. Min Act: -0.0000

Data Index: 527511 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.2989. Min Act: -0.0000

Data Index: 1246264 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 4.9714. Min Range: -4.9714

Max Act: 3.6973. Min Act: -0.0000

Data Index: 832082 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 4.9714. Min Range: -4.9714

Max Act: 3.7241. Min Act: -0.0000

Data Index: 1173585 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 4.9714. Min Range: -4.9714

Max Act: 3.7328. Min Act: -0.0000

Data Index: 1039677 (C4 (Web Text))

Max Activating Token Index: 35